diff --git a/crates/ml/src/cuda_pipeline/common_device_functions.cuh b/crates/ml/src/cuda_pipeline/common_device_functions.cuh
index eb26c4998..42e99435c 100644
--- a/crates/ml/src/cuda_pipeline/common_device_functions.cuh
+++ b/crates/ml/src/cuda_pipeline/common_device_functions.cuh
@@ -440,6 +440,9 @@ __device__ __forceinline__ void cooperative_load_bias_bf16_to_f32(
         shmem_dst[i] = __bfloat162float(global_src[i]);
 }
 
+/* Forward declaration — defined below, used by BF16 matvec helpers */
+__device__ float warp_reduce_sum_all(float val);
+
 /**
  * Warp-cooperative matrix-vector multiply with BF16 weights, F32 accumulation.
  *